# Recurse.run // by Synnada Team

- **Event:** [GPT-6 Astra Hackathon SF](https://cerebralvalley.ai/e/openai-gpt-6-astra-sf)
- **When:** Tue, Sep 8 at 9:00 AM – 10:00 PM (PDT)
- **Where:** San Francisco, CA
- **Team:** [Sami Tandogdu](https://cerebralvalley.ai/u/scannerdarkly)
- **GitHub:** https://github.com/synnada-ai/recurse-sdk/tree/main/examples/backpack-3d
- **Demo video:** https://youtu.be/pvwV1E9xr54
- **Gallery:** https://cerebralvalley.ai/e/openai-gpt-6-astra-sf/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/openai-gpt-6-astra-sf/hackathon/gallery/47

Astra is good at creating 3D objects through Blender. What if we could make it great by letting it see, critique, and improve its own work?

Our project turns a 2D image and a description into a 3D model through repeated visual refinement. The agent builds a model, renders it, compares the result with the reference, and tries again—adjusting shapes, proportions, and details along the way.

Codex creates this recursive agent and its custom modeling tools. GPT-6 Astra powers the agent, and Recurse provides the serverless harness and runtime where its loop runs.
The idea is simple: give Astra more than one shot. Give it an environment where it can turn visual feedback into better 3D models, with downloadable outputs and an inspectable history of its attempts.

NOTE: We are submitting NOT the whole repo (which is our SDK), but just backpack-3d example.

---

Markdown version of https://cerebralvalley.ai/e/openai-gpt-6-astra-sf/hackathon/gallery/47. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt